sepehr
e706cef5d6
All checks were successful
Deploy to Production / Build and Deploy (push) Successful in 2m44s
ROOT CAUSE FIX: PyMuPDF silently raised AttributeError when fontname=None was passed to insert_textbox. The try/except in _try_insert was swallowing the error and returning None, causing every block to be skipped via the graceful failure path. Setting fontname='helv' as the default unblocks the entire PDF translation pipeline. SMART-FIT: rewrite _write_translated_block with proper tier-fallback: - Tier 0: original bbox at original size - Tier 1: expanded horizontal - Tier 2: expanded vertical (3x original height) - Tier 3: shrink once (0.93x) - Tier 4: shrink twice (0.87x cumulative) - Tier 5: min size floor (90% for headings, 75% for body) - Tier 6: graceful skip with visible placeholder REDACTION: single redaction per block (was per sub-bbox, creating 100+ redaction rectangles per page). Now only 1 redaction per text block. FEATURE FLAG: PDF_SMART_FIT_ENABLED (default true, observation-first). METRICS: text_overflow -> format_elements_lost_total. RESULT ON REAL PDF: Before: fonts shrunk 22pt->5.6pt, hierarchy destroyed After: fonts EXACT match: [8, 11, 12, 14, 16, 22] preserved
47 lines
1.7 KiB
Python
47 lines
1.7 KiB
Python
"""Test smart-fit with mock translation (same length) to isolate the issue."""
|
|
import sys
|
|
sys.path.insert(0, '.')
|
|
import importlib.util
|
|
import fitz
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
spec = importlib.util.spec_from_file_location('pdf_mod', 'translators/pdf_translator.py')
|
|
pdf_mod = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(pdf_mod)
|
|
|
|
# Mock the translation to return the original text (no length change)
|
|
def mock_translate(self, text, target_lang, source_lang):
|
|
return text # No change
|
|
|
|
PDFTranslator = pdf_mod.PDFTranslator
|
|
with patch.object(PDFTranslator, '_translate_single', mock_translate):
|
|
PDFTranslator().translate_file(
|
|
Path('sample_files/test_corpus/test_pdf.pdf'),
|
|
Path('sample_files/test_corpus/test_pdf_no_translation.pdf'),
|
|
target_language='fr',
|
|
source_language='en',
|
|
)
|
|
|
|
# Check fonts
|
|
o = fitz.open('sample_files/test_corpus/test_pdf.pdf')
|
|
n = fitz.open('sample_files/test_corpus/test_pdf_no_translation.pdf')
|
|
print(f"=== Mock translation (no length change) ===")
|
|
print(f"Original: {len(o)} pages, {o.page_count} blocks")
|
|
print(f"Translated: {len(n)} pages")
|
|
for i in [0]:
|
|
o_sizes = set()
|
|
n_sizes = set()
|
|
for b in o[i].get_text("dict").get("blocks", []):
|
|
for l in b.get("lines", []):
|
|
for s in l.get("spans", []):
|
|
o_sizes.add(round(s.get("size", 0), 1))
|
|
for b in n[i].get_text("dict").get("blocks", []):
|
|
for l in b.get("lines", []):
|
|
for s in l.get("spans", []):
|
|
n_sizes.add(round(s.get("size", 0), 1))
|
|
print(f" Page 1 Original: {sorted(o_sizes)}")
|
|
print(f" Page 1 Translated: {sorted(n_sizes)}")
|
|
o.close()
|
|
n.close()
|